Agile Adaptive Control
The agile adaptive control algorithm addresses slow learning in autonomous vehicles by updating design parameters using an agile learning model, enhancing responsiveness and accuracy without additional calibration, thus improving safety and performance.
DE102025104317B3Active Publication Date: 2026-06-03GM GLOBAL TECHNOLOGY OPERATIONS LLC
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Filing Date
- 2025-02-06
- Publication Date
- 2026-06-03
Smart Images
Figure 00000000_0000_ABST
Abstract
A method using agile adaptive control (A2C) includes receiving planning data, which encompasses a desired vehicle path, as input to an agile adaptive control model, and receiving vehicle data as input to the agile adaptive control model. The method further includes determining, based on the planning and vehicle data, that a vehicle position error exceeds a position threshold, and initiating an agile learning model of the adaptive control model to update initial adaptive design parameters based on the planning and vehicle data. The method also includes generating updated adaptive design parameters and generating a control command using a control model of the adaptive control model based on the updated adaptive design parameters.
Need to check novelty before this filing date? Find Prior Art